Complementarity×framework
A body of knowledge · human–AI delivery

Collaboration Begins Here

Two dissimilar intelligences, each positioned to catch the other's failure modes. This is the engineering discipline for pairing them — and it is free to read, question, and use.

Technological advances are occuring faster than ever. Evolving our strengths, limitations, and failure modes to the point they cannot be permanently assigned. Under this framework rigor is a spectrum continously assessed; capability, ethical performance, moral status, and authority remain separate questions. This framework takes these realities, pairing us, and bridging novelty when an advance tomorrow can change the very landscape underneath.

Duality is not decoration here. It is the argument.
The spine · fourteen movements

Fourteen principles that survive all tailoring

Each states a belief the framework will not bend. Read them in descent, or jump to any one from the index. Watch each demonstration, every motion here is the principle, not decoration.

The reference layer · the corpus beneath

The principles are the surface. This is the depth.

Seven parts, forty-two chapters, organized so you can feel the architecture without reading it linearly. A visitor who read only the fourteen movements already has the whole argument; everything here is for when you want to operate it.

Human layer · forty-two chapters

Enter through the summary. Open only the depth you need.

Choose a part and chapter. Highlights remain visible; governing boundaries, evidence, collaboration guidance, failure modes, and inspection prompts open progressively.

Visible: human comprehension and inspection.
Embedded, non-rendered: the complete authoritative agent corpus for machine consumption.
Object 01

The lifecycle & its gates

Eight stages, each ending in a decision gate that releases funding on evidence — not on the calendar. Select a stage; see what the gate demands and what it commits.

Object 02

Ethical legitimacy is a path, not a late review

A capability is not eligible merely because it is feasible, valuable, safe enough, or compliant. The framework asks the question before funding the approach, compares alternatives, and renews the answer in operation.

G1 · problem worth solving
  • Identify affected people and any materially affected Agents.
  • Record rights, agency, power, distribution, foreseeable harm, dissent, recourse, and uncertainty.
  • Establish a proportionate provisional legitimacy conclusion.
G2 · approach justified
  • Compare credible alternatives on ethical legitimacy—not only cost, risk, or compliance.
  • Keep disagreement visible; do not convert unknown into approval.
  • Fund only the next bounded commitment.

Operational renewal

Reassess when scope, authority, allocation, affected parties, evidence, or operating conditions change. When an Agent may be materially affected by modification, copying, deletion, or delegated conditions, assess possible moral consideration separately from its capability, ethical performance, legal standing, ownership, or authority.

Object 03

The teaming patterns

The framework's most portable contribution: a pattern language for pairing, each pattern named by the failure mode it covers. The bracket ⌐¬ means "each covers the other" — never a merge.

Object 04

The automation spectrum

Work is decomposed to the decision, not the job. Every decision gets an allocation — including the prohibition class: work that should not be automated, with the reason recorded.

Object 05

Consequence & transition tempo

Two coupled dials. Consequence sets how much framework you need; tempo sets how fast you move. Rapid is forbidden above a consequence ceiling — and the reversibility ratchet can force you slower still.

Consequence classLow
LowCatastrophic
Transition tempo
Slow
Medium
Rapid
parallel-runfast cutover
At low consequence, almost any tempo is legitimate. Raise consequence and watch the fast bands close — the framework materializes in proportion.
Object 06

The survives-the-burst test

A counter-cyclical filter run at the funding gates. It starves hype-driven bets before a crash and keeps funding evidence-backed winners through the trough. All three predicates must hold. Toggle them.

Would not survive

Never let capital run ahead of evidence.

Bubble exposure is a managed risk, not a forecast to get right. The test is the machine-checkable half of that discipline.

Object 07

The eleven properties

A conjunctive mandate — all eleven must hold together. Not a score, not a ranking, not a progress meter. Hover any one: the rest dim, because the failure of any single property can invalidate the capability.

The mandate applies to the framework's own execution substrate, too.
Object 08

The anti-patterns catalog

Twenty-two ways delivery fails. The catalog doubles as the Sentinel's monitoring specification: where a failure is machine-detectable, it is tagged sentinel. Select any to open it.

The whole framework · ninety seconds

If you read nothing else

Deliver AI capability the way you would deliver anything whose value is uncertain, whose cost outlives its launch, and whose behavior drifts — but do it with AI on the team, not just under the microscope. Move money when evidence arrives. Scale rigor to consequence. Design the boundary between human and machine so it is observable and reversible. Point oversight both ways. Keep accountability human. Name the workforce cost out loud. And never let capital run ahead of evidence.

Principles ten through fourteen are the framework's distinctive claims — the arrival, not the coda.